from datasets import load_dataset
dataset = load_dataset("ShengbinYue/DISC-Law-SFT")
----------------------------------------------------------------------------------
error:
Generating train split: 166758 examples [00:00, 184286.58 examples/s]
Traceback (most recent call last):
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/builder.py", line 1940, in _prepare_split_single
writer.write_table(table)
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/arrow_writer.py", line 572, in write_table
pa_table = table_cast(pa_table, self._schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/table.py", line 2328, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/table.py", line 2286, in cast_table_to_schema
raise ValueError(f"Couldn't cast\n{table.schema}\nto\n{features}\nbecause column names don't match")
ValueError: Couldn't cast
id: string
reference: list<item: string>
child 0, item: string
input: string
output: string
to
{'id': Value(dtype='string', id=None), 'input': Value(dtype='string', id=None), 'output': Value(dtype='string', id=None)}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/load.py", line 2153, in load_dataset
builder_instance.download_and_prepare(
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/builder.py", line 954, in download_and_prepare
self._download_and_prepare(
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/builder.py", line 1049, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/builder.py", line 1813, in _prepare_split
for job_id, done, content in self._prepare_split_single(
File "/home/ysx/miniconda3/lib/python3.11/site-packages/datasets/builder.py", line 1958, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.builder.DatasetGenerationError: An error occurred while generating the dataset